© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250861
    Prev
    Next
    INDEX
    Explanations

    corrective actions or infringements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EM
    0.48
     elig
    0.46
     E
    0.46
    صل
    0.45
    FH
    0.43
     Pritchard
    0.43
     modes
    0.43
    翁
    0.42
     pequeños
    0.42
     đạt
    0.41
    POSITIVE LOGITS
     mismanagement
    0.53
     अनदे
    0.49
     ഇടപെ
    0.48
    উন্ট
    0.46
     corrective
    0.46
     infringe
    0.46
     Tagen
    0.45
     smuggling
    0.45
    矯
    0.45
    矯正
    0.44
    Activations Density 0.002%

    No Known Activations